{"id":"W3197766881","doi":"10.25189/2675-4916.2021.v2.n3.id399","title":"Quantifying the Differences Between Lexical Categories","year":2021,"lang":"en","type":"article","venue":"Cadernos de Linguística","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Humber Polytechnic","funders":"","keywords":"Linguistics; Categorization; Determinative; Computer science; Natural language processing; Grammar; Pronoun; Psychology; Artificial intelligence; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005720358,0.00040248,0.0005659414,0.004387066,0.0008876417,0.004637055,0.0009347955,0.0009688105,0.004640824],"category_scores_gemma":[0.05487227,0.0002890672,0.000498282,0.003882549,0.002980144,0.007006085,0.003858648,0.001361805,0.001029985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028294,"about_ca_system_score_gemma":0.0006648179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001753823,"about_ca_topic_score_gemma":0.001826997,"domain_scores_codex":[0.991926,0.003038892,0.0007705859,0.001806548,0.002065425,0.0003925684],"domain_scores_gemma":[0.9705271,0.02176116,0.001475672,0.003249953,0.002517857,0.0004682809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001365359,0.0002511005,0.1637419,0.0006996607,0.0005014411,0.0002901968,0.01786283,0.004709045,0.03053943,0.3398588,0.004754345,0.4354258],"study_design_scores_gemma":[0.00006108145,0.0004774294,0.2213525,0.000193438,0.000165266,0.0007510697,0.01586437,0.02465451,0.009301377,0.703847,0.02313796,0.0001939939],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7868524,0.00112209,0.1663334,0.0006776954,0.0001548874,0.0001662969,0.001811443,0.0002663171,0.04261541],"genre_scores_gemma":[0.9692206,0.0001211698,0.02839275,0.00009689607,0.00003312205,0.0001221466,0.0009538825,0.0001089446,0.0009504979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005720358,"threshold_uncertainty_score":0.03025252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06088552525081525,"score_gpt":0.3226802791093785,"score_spread":0.2617947538585633,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}